How can I preprocess NLP text (lowercase, remove special characters, remove numbers, remove emails, etc) in one pass?

Question

How can I preprocess NLP text (lowercase, remove special characters, remove numbers, remove emails, etc) in one pass using Python?

Here are all the things I want to do to a Pandas dataframe in one pass in python:
1. Lowercase text
2. Remove whitespace
3. Remove numbers
4. Remove special characters
5. Remove emails
6. Remove stop words
7. Remove NAN
8. Remove weblinks
9. Expand contractions (if possible not necessary)
10. Tokenize

Here's how I am doing it all individually:

    def preprocess(self, dataframe):


    self.log.info("In preprocess function.")

    dataframe1 = self.remove_nan(dataframe)
    dataframe2 = self.lowercase(dataframe1)
    dataframe3 = self.remove_whitespace(dataframe2)

    # Remove emails and websites before removing special characters
    dataframe4 = self.remove_emails(self, dataframe3)
    dataframe5 = self.remove_website_links(self, dataframe4)

    dataframe6 = self.remove_special_characters(dataframe5)
    dataframe7 - self.remove_numbers(dataframe6)
    self.remove_stop_words(dataframe8) # Doesn't return anything for now
    dataframe7 = self.tokenize(dataframe6)

    self.log.info(f"Sample of preprocessed data: {dataframe4.head()}")

    return dataframe7

def remove_nan(self, dataframe):
    """Pass in a dataframe to remove NAN from those columns."""
    return dataframe.dropna()

def lowercase(self, dataframe):
    logging.info("Converting dataframe to lowercase")
    lowercase_dataframe = dataframe.apply(lambda x: x.lower())
    return lowercase_dataframe


def remove_special_characters(self, dataframe):
    self.log.info("Removing special characters from dataframe")
    no_special_characters = dataframe.replace(r'[^A-Za-z0-9 ]+', '', regex=True)
    return no_special_characters

def remove_numbers(self, dataframe):
    self.log.info("Removing numbers from dataframe")
    removed_numbers = dataframe.str.replace(r'\d+','')
    return removed_numbers

def remove_whitespace(self, dataframe):
    self.log.info("Removing whitespace from dataframe")
    # replace more than 1 space with 1 space
    merged_spaces = dataframe.str.replace(r"\s\s+",' ')
    # delete beginning and trailing spaces
    trimmed_spaces = merged_spaces.apply(lambda x: x.str.strip())
    return trimmed_spaces

def remove_stop_words(self, dataframe):
    # TODO: An option to pass in a custom list of stopwords would be cool.
    set(stopwords.words('english'))

def remove_website_links(self, dataframe):
    self.log.info("Removing website links from dataframe")
    no_website_links = dataframe.str.replace(r"http\S+", "")
    return no_website_links

def tokenize(self, dataframe):
    tokenized_dataframe = dataframe.apply(lambda row: word_tokenize(row))
    return tokenized_dataframe

def remove_emails(self, dataframe):
    no_emails = dataframe.str.replace(r"\S*@\S*\s?")
    return no_emails

def expand_contractions(self, dataframe):
    # TODO: Not a priority right now. Come back to it later.
    return dataframe

Answer 1

The following function performs all things you have mentioned.

import nltk
from nltk.tokenize import RegexpTokenizer
from nltk.stem import WordNetLemmatizer,PorterStemmer
from nltk.corpus import stopwords
import re
lemmatizer = WordNetLemmatizer()
stemmer = PorterStemmer() 

 def preprocess(sentence):
    sentence=str(sentence)
    sentence = sentence.lower()
    sentence=sentence.replace('{html}',"") 
    cleanr = re.compile('<.*?>')
    cleantext = re.sub(cleanr, '', sentence)
    rem_url=re.sub(r'http\S+', '',cleantext)
    rem_num = re.sub('[0-9]+', '', rem_url)
    tokenizer = RegexpTokenizer(r'\w+')
    tokens = tokenizer.tokenize(rem_num)  
    filtered_words = [w for w in tokens if len(w) > 2 if not w in stopwords.words('english')]
    stem_words=[stemmer.stem(w) for w in filtered_words]
    lemma_words=[lemmatizer.lemmatize(w) for w in stem_words]
    return " ".join(filtered_words)


df['cleanText']=df['Text'].map(lambda s:preprocess(s)) 

Answer 2

I decided to use Dask, which allows you to parallelize Python tasks on your local computer and works well with Pandas, numpy, and scikitlearn: http://docs.dask.org/en/latest/why.html